Why does working with a transposed tensor not make the following operations less performant?

• Arraymancer

  21 1,307 8.2 Nim

  A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

Here are my repacking procedures: - https://github.com/mratsim/Arraymancer/blob/2c4a39fb/src/arraymancer/laser/primitives/matrix_multiplication/gemm_packing.nim#L24-L99

• laser

  6 261 3.6 Nim

  The HPC toolbox: fused matrix multiplication, convolution, data-parallel strided tensor primitives, OpenMP facilities, SIMD, JIT Assembler, CPU detection, state-of-the-art vectorized BLAS for floats and integers (by mratsim)

  

For convolutions: - https://github.com/numforge/laser/blob/e23b5d63/research/convolution_optimisation_resources.md

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project